Tweeted By @yudapearl

1/5
For readers wishing to sharpen their understanding of RL and CI, recall how we answered the question: "How can RL optimize policies without a causal model?".
We said: RL is on Level-2 of the Ladder because it receives data from controlled interventions. #Bookofwhy

— Judea Pearl (@yudapearl) December 2, 2018